From 76177aa280494bb36d7a0bcbda1078d4db717020 Mon Sep 17 00:00:00 2001
From: Ali Labbene <ali.labbene@st.com>
Date: Mon, 9 Dec 2019 11:25:19 +0100
Subject: Official ARM version: v4.5

---
 DSP_Lib/Source/BasicMathFunctions/arm_mult_q7.c | 127 ++++++++++++++++++++++++
 1 file changed, 127 insertions(+)
 create mode 100644 DSP_Lib/Source/BasicMathFunctions/arm_mult_q7.c

(limited to 'DSP_Lib/Source/BasicMathFunctions/arm_mult_q7.c')

diff --git a/DSP_Lib/Source/BasicMathFunctions/arm_mult_q7.c b/DSP_Lib/Source/BasicMathFunctions/arm_mult_q7.c
new file mode 100644
index 0000000..c2b50b6
--- /dev/null
+++ b/DSP_Lib/Source/BasicMathFunctions/arm_mult_q7.c
@@ -0,0 +1,127 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010-2014 ARM Limited. All rights reserved.    
+*    
+* $Date:        19. March 2015
+* $Revision: 	V.1.4.5
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:	    arm_mult_q7.c    
+*    
+* Description:	Q7 vector multiplication.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Redistribution and use in source and binary forms, with or without 
+* modification, are permitted provided that the following conditions
+* are met:
+*   - Redistributions of source code must retain the above copyright
+*     notice, this list of conditions and the following disclaimer.
+*   - Redistributions in binary form must reproduce the above copyright
+*     notice, this list of conditions and the following disclaimer in
+*     the documentation and/or other materials provided with the 
+*     distribution.
+*   - Neither the name of ARM LIMITED nor the names of its contributors
+*     may be used to endorse or promote products derived from this
+*     software without specific prior written permission.
+*
+* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+* FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE 
+* COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
+* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
+* BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
+* ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+* POSSIBILITY OF SUCH DAMAGE. 
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**    
+ * @ingroup groupMath    
+ */
+
+/**    
+ * @addtogroup BasicMult    
+ * @{    
+ */
+
+/**    
+ * @brief           Q7 vector multiplication    
+ * @param[in]       *pSrcA points to the first input vector    
+ * @param[in]       *pSrcB points to the second input vector    
+ * @param[out]      *pDst points to the output vector    
+ * @param[in]       blockSize number of samples in each vector    
+ * @return none.    
+ *    
+ * <b>Scaling and Overflow Behavior:</b>    
+ * \par    
+ * The function uses saturating arithmetic.    
+ * Results outside of the allowable Q7 range [0x80 0x7F] will be saturated.    
+ */
+
+void arm_mult_q7(
+  q7_t * pSrcA,
+  q7_t * pSrcB,
+  q7_t * pDst,
+  uint32_t blockSize)
+{
+  uint32_t blkCnt;                               /* loop counters */
+
+#ifndef ARM_MATH_CM0_FAMILY
+
+/* Run the below code for Cortex-M4 and Cortex-M3 */
+  q7_t out1, out2, out3, out4;                   /* Temporary variables to store the product */
+
+  /* loop Unrolling */
+  blkCnt = blockSize >> 2u;
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.    
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+    /* C = A * B */
+    /* Multiply the inputs and store the results in temporary variables */
+    out1 = (q7_t) __SSAT((((q15_t) (*pSrcA++) * (*pSrcB++)) >> 7), 8);
+    out2 = (q7_t) __SSAT((((q15_t) (*pSrcA++) * (*pSrcB++)) >> 7), 8);
+    out3 = (q7_t) __SSAT((((q15_t) (*pSrcA++) * (*pSrcB++)) >> 7), 8);
+    out4 = (q7_t) __SSAT((((q15_t) (*pSrcA++) * (*pSrcB++)) >> 7), 8);
+
+    /* Store the results of 4 inputs in the destination buffer in single cycle by packing */
+    *__SIMD32(pDst)++ = __PACKq7(out1, out2, out3, out4);
+
+    /* Decrement the blockSize loop counter */
+    blkCnt--;
+  }
+
+  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.    
+   ** No loop unrolling is used. */
+  blkCnt = blockSize % 0x4u;
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+  /* Initialize blkCnt with number of samples */
+  blkCnt = blockSize;
+
+#endif /* #ifndef ARM_MATH_CM0_FAMILY */
+
+
+  while(blkCnt > 0u)
+  {
+    /* C = A * B */
+    /* Multiply the inputs and store the result in the destination buffer */
+    *pDst++ = (q7_t) __SSAT((((q15_t) (*pSrcA++) * (*pSrcB++)) >> 7), 8);
+
+    /* Decrement the blockSize loop counter */
+    blkCnt--;
+  }
+}
+
+/**    
+ * @} end of BasicMult group    
+ */
-- 
cgit